Partitional Clustering Research Articles

Comparative analysis of ANFIS models in Prediction of Streamflow: the case of Seyhan Basin

In order to sustain human life without problems, a rational planning is required for the conservation and use of existing water resources. The potential of future water sources should be determined as the first step in such planning. Therefore, river flow forecasting is necessary to provide basic information about a variety of problems related to the operation of river systems. In this study, the long-term daily flow values of the Zamantı River-Değirmenocağı, Zamantı River-Ergenuşağı, and Eğlence River-Eğribük stations in the Seyhan Basin in Turkey were examined. In order to predict the forward flow rate from past flow measurement values, the Adaptative Neuro-Fuzzy Inference System (ANFIS) model was trained using Backpropagation (BP), Hybrid Learning (HB), and Simulated Annealing (SA) algorithms, and the results were compared. The performance of ANFIS models created with different input parameters using Grid Partitioning (GP) and Fuzzy C-Means Clustering (FCM) methods was also examined. The evaluation criteria used for comparison were Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Determination Coefficient (R2), and Mean Absolute Percentage Error (MAPE). The best results for R2 values of 0.6854, 0.9242, and 0.9373 were obtained for FMSs using the BP model. As a result of the analysis, it was concluded that the BP algorithm could be used more successfully and effectively than other algorithms for training ANFIS parameters in nonlinear problems.

A dynamic adaptive iterative clustered federated learning scheme

Clustered federated learning (CFL), as an important research branch of personalized federated learning (FL), can better cope with the highly statistically heterogeneous federated learning environment and provide higher quality services to clients. However, existing CFL schemes have difficulties in adapting to real-time data distribution changes due to disadvantages such as relatively fixed cluster structure. This poses a great challenge to the practical deployment of CFL schemes. To address the common problems of existing CFL schemes, we propose a more flexible dynamic adaptive cluster federated learning scheme (AICFL). AICFL uses the mutual sensitivity between models and data as intuition to perform cluster identity estimation, cluster addition, cluster model updating, and cluster deletion in the early iterations of FL to find the optimal client cluster partitioning. Firstly, this process does not require a priori estimation of the number of clusters and does not require the online participation of all clients. Secondly, during cluster partitioning, AICFL is able to adjust the cluster structure in real time based on the overall data distribution. Moreover, AICFL has the same ability to adapt to changes in the system environment in the middle and late stages of FL. The experimental results show that our scheme gives the most reasonable cluster partitioning results in all cases which indicates that AICFL is able to cope with the above-mentioned distribution changes well, and has better adaptability and better flexibility than other schemes.

A Partitional Clustering Approach for the Identification and Analysis of Coexisting Bacteria in Groups of Bacterial Vaginosis Patients

A Partitional Clustering Approach for the Identification and Analysis of Coexisting Bacteria in Groups of Bacterial Vaginosis Patients

Evolutionary optimization of biogas production from food, fruit, and vegetable (FFV) waste

The success of anaerobic digestion (AD) process for biogas production is contingent upon complex mix of operating factors, process conditions, and feedstock types, which could be affected by inadequate understanding of microbial, kinetic, and physicochemical processes. To address these limitations, efforts have been directed toward developing mathematical and intelligent models. Although mathematical models provide near-optimal solutions, they are time consuming, highly expensive, and demanding. Intelligent standalone models are also limited by their low predictive capability and inability to guarantee global optimal solution for the prediction of cumulative biogas yield for FFV waste. However, hyperparameter optimization of such models is essential to improve the prediction performance for cumulative biogas yield for FFV waste. Therefore, this study applies a genetic algorithm (GA) to optimize an adaptive neuro-fuzzy inference system (ANFIS) for the prediction of cumulative biogas production. Seven (7) input variables, organic loading rate (OLR), volatile solids (VS), pH, hydraulic retention time (HRT), temperature, retention time, and reaction volume, were considered with cumulative biogas production as the output. The effect of varying clustering techniques was evaluated. The three (3) clustering techniques evaluated are fuzzy c-means and subtractive clustering and grid partitioning. The hybrid model was evaluated based on some verified statistical performance metrics. Optimal root mean squared error (RMSE), mean absolute deviation (MAD), mean absolute percentage error (MAPE), and standard deviation error (error STD) of 0.0529, 0.0326,7.6742, and 0.0474, respectively, were reported at the model testing phase for the subtractive clustering technique being the best-performing model. The results confirm the capacity of hybrid evolutionary (genetic) algorithm based on subtractive clustering technique to predict the biogas yield from FFV and serve as an effective tool for the upscaling of anaerobic digestion units as well as in techno-economic studies toward more efficient energy utilization.Graphical abstract

Role of gut microbiota in perioperative neurocognitive disorders after cardiopulmonary bypass surgery in rats with humanized gut flora

To investigate whether gut microbiota disturbance after cardiopulmonary bypass (CPB) contributes to the development of perioperative neurocognitive disorders (PND). Fecal samples were collected from healthy individuals and patients with PND after CPB to prepare suspensions of fecal bacteria, which were transplanted into the colorectum of two groups of pseudo-germ-free adult male SD rats (group NP and group P, respectively), with the rats without transplantation as the control group (n=10). The feces of the rats were collected for macrogenomic sequencing analysis, and serum levels of IL-1β, IL-6 and TNF-α were measured with ELISA. The expression levels of GFAP and p-Tau protein in the hippocampus of the rats were detected using Western blotting, and the cognitive function changes of the rats were assessed with Morris water maze test. In all the 3 groups, macrogenomic sequencing analysis showed clustering and clear partitions of the gut microbiota after the transplantation. The relative abundances of Klebsiella in the control group (P < 0.005), Akkermansia in group P (P < 0.005) and Bacteroides in group NP (P < 0.005) were significantly increased after the transplantation. Compared with those in the control group, the rats in group NP and group P showed significantly decreased serum levels of IL-1β, IL-6 and TNF-α and lowered expression levels of GFAP and p-Tau proteins (all P < 0.05). Escape platform crossings and swimming duration in the interest quadrant increased significantly in group NP (P < 0.05), but the increase was not statistically significant in group N. Compared with those in group P, the rats in group NP had significantly lower serum levels of IL-1β, IL-6 and TNF-α and protein expressions of GFAP and p-Tau (all P < 0.05) with better performance in water maze test (P < 0.05). In patients receiving CPB, disturbances in gut mirobiota contributes to the development of PND possibly in relation with inflammatory response.

Some Clustering Methods, Algorithms and their Applications

Clustering is a type of unsupervised learning [15]. When no target values are known, or "supervisors," in an unsupervised learning task, the purpose is to produce training data from the inputs themselves. Data mining and machine learning would be useless without clustering. If you utilize it to categorize your datasets according to their similarities, you'll be able to predict user behavior more accurately. The purpose of this research is to compare and contrast three widely-used data-clustering methods. Clustering techniques include partitioning, hierarchy, density, grid, and fuzzy clustering. Machine learning, data mining, pattern recognition, image analysis, and bioinformatics are just a few of the many fields where clustering is utilized as an analytical technique. In addition to defining the various algorithms, specialized forms of cluster analysis, linking methods, and please offer a review of the clustering techniques used in the big data setting.

Multi-view subspace clustering via adaptive graph learning and late fusion alignment

Multi-view subspace clustering has attracted great attention due to its ability to explore data structure by utilizing complementary information from different views. Most of existing methods learn a sample representation coefficient matrix or an affinity graph for each single view, then the final clustering result is obtained from the spectral embedding of a consensus graph using certain traditional clustering techniques, such as k-means. However, clustering performance will be degenerated if the early fusion of partitions cannot fully exploit relationships between all samples. Different from existing methods, we propose a multi-view subspace clustering method via adaptive graph learning and late fusion alignment (AGLLFA). For each view, AGLLFA learns an affinity graph adaptively to capture the similarity relationship among samples. Moreover, a spectral embedding learning term is designed to exploit the latent feature space of different views. Furthermore, we design a late fusion alignment mechanism to generate an optimal clustering partition by fusing view-specific partitions obtained from multiple views. An alternate updating algorithm with validated convergence is developed to solve the resultant optimization problem. Extensive experiments on several benchmark datasets are conducted to illustrate the effectiveness of the proposed method when compared with other state-of-the-art methods. The demo code of this work is publicly available at https://github.com/tangchuan2000/AGLLFA.

A Novel Voltage/var Sensitivity Calculation Method to Partition the Distribution Network Containing Renewable Energy

Abstract: As the current calculation method of voltage/var sensitivity (VVS) could not reflect the temporal variations of power sources and load, the paper proposes a novel VVS calculation method to partition the distribution network containing renewable energy. Firstly, the defects of the existing VVS calculation methods are analyzed, and a novel VVS calculation method is proposed by adding reactive power output perturbation to the reactive power source. Secondly, the VVS matrix is fuzzified to obtain the membership matrix between each node. Based on the membership relationship between the reactive power source nodes, the nodes with a strong coupling relationship are merged to determine the initial number of partitioning. Then, the final partitioning result is determined according to the affiliation between each load node and each reactive power source. Finally, the partitioning result is evaluated based on the partitioning membership indexes. The proposed approach is tested on the IEEE 33-node distribution test system, and numerical simulations verify the high efficiency of partitioning. The simulation results show that the proposed method can reflect the temporal variations of power sources and load, and ensure the reasonable distribution of voltage and reactive power in each zone. Background: The voltage/var control of the power system is an important means to ensure the safe and economically stable operation of the system. Objective: The paper proposes a novel VVS calculation method to partition the distribution network containing renewable energy. Method: Firstly, the existing problems of electrical distance index are analyzed. A novel VVS matrix calculation method is proposed, which calculates the VVS of each reactive power source to the remaining nodes by adding voltage/var output perturbation to the reactive power source. Secondly, the VVS matrix is fuzzified to obtain the membership matrix between each node. Based on the membership relationship between the reactive power source nodes, the power supply nodes with strong coupling relationship are merged to determine the initial number of the partitioning. Then, the final partitioning result is determined according to the affiliation between each load node and each reactive power source. Finally, the partitioning result is evaluated based on the sensitivity index of membership degree. Results: The proposed approach is tested on the IEEE 33-node distribution test system and numerical simulations verify high efficiency of the partitioning. The simulation results show that the proposed method can reflect the temporal variations of power sources and load, and ensure the reasonable distribution of voltage and reactive power in each zone. Conclusion: The proposed method can reflect the temporal variations of power sources and load, and ensure the reasonable distribution of voltage and reactive power in each zone. This paper proposed a fuzzy clustering partitioning based on a novel calculation method of VVS, which is suitable for the problem of variable voltage /var running state of the system under high-proportion DG access.

Unified One-Step Multi-View Spectral Clustering

Multi-view spectral clustering, which exploits the complementary information among graphs of diverse views to obtain superior clustering results, has attracted intensive attention recently. However, most existing multi-view spectral clustering methods obtain the clustering partitions in a two-step scheme, i.e., spectral embedding and subsequent k-means. This two-step scheme inevitably seeks sub-optimal clustering results due to the information loss during the two-steps processes. Besides, existing multi-view spectral clustering methods do not jointly utilize the information of graphs and embedding matrices, which also degrades final clustering results. To solve these issues, we propose a unified one-step multi-view spectral clustering method, which integrates the spectral embedding and <formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex>$k$</tex></formula> -means into a unified framework to obtain discrete clustering labels with a one-step strategy. Under the observation that the inner product of the embedding matrix is a low-rank approximation of the graph, we combine graphs and embedding matrices of different views to obtain a unified graph. Then, we directly capture the discrete clustering indicator matrix from the unified graph. Furthermore, we design an effective optimization algorithm to solve the resultant problem. Finally, a set of experiments on various datasets are conducted to verify the effectiveness of the proposed method. The demo code of this work is publicly available at https://github.com/guanyuezhen/UOMvSC.

Hierarchical Machine Learning of Low-Resolution Coarse-Grained Free Energy Potentials.

A force-matching-based method for supervised machine learning (ML) of coarse-grained (CG) free energy (FE) potentials─known as multiscale coarse-graining via force-matching (MSCG/FM)─is an efficient method to develop microscopically informed CG models that are thermodynamically and statistically equivalent to the reference microscopic models. For low-resolution models, when the coarse-graining is at supramolecular scales, objective-oriented clustering of nonbonded particles is required and the reduced description becomes a function of the clustering algorithm. In the present work, we explore the dependence of the ML of the CG Helmholtz FE potential on the clustering algorithm. We consider coarse-graining based on partitional (k-means, leading to Voronoi diagram) and hierarchical agglomerative (bottom-up) clustering algorithms common in unsupervised ML and develop theory connecting the MSCG/FM learned CG Helmholtz potential and the clustering statistics. By combining the agglomerative clustering and the MSCG/FM learning in a recursive manner, we propose an efficient ML methodology to develop the fine-to-low resolution hierarchies of the CG models. The methodology does not suffer from degrading accuracy or increased computational cost to construct larger hierarchies and as such does not impose an upper size limitation of the CG particles resulting from the extended hierarchies. The utility of the methodology is demonstrated by obtaining the bottom-up agglomerative hierarchy for liquid nitromethane from all-atom molecular dynamics (MD) simulations. For agglomerative hierarchies, we prove the existence of renormalization group transformations that indicate self-similarity and allow for learning the low-resolution MSCG/FM potentials at low computational cost by rescaling and renormalizing the certain finer-resolution members of the hierarchy. The hierarchies of the CG models can be used to carry out simulations under constant-pressure conditions.

Combined Application of Partition Clustering Classification and Gerchberg-Papoulis Optimization Algorithm for Spherical Near Field Antenna Measurements

An adaptive sampling and optimized extrapolation scheme for spherical near-field antenna testing is proposed. The method relies on the partition clustering classification algorithm and Voronoi classification to divide a small amount of initial data into subclasses and cells. The sampling density and rates of variation between adjacent sampling points are used as an overall metric function to evaluate the sampling dynamics at each location. Appropriate interpolation is performed in the highly dynamic region to increase the effective data in the near-field samples. The Gerchberg-Papoulis algorithm extrapolates the unnecessary interpolation region to improve the near-field sampling accuracy. This method uses a small amount of initial near-field sampled data for near-far field conversion to achieve the same precision as uniform oversampling. The feasibility and stability of the algorithm are proved from the actual measurement results.

Cluster Partition-Based Voltage Control Combined Day-Ahead Scheduling and Real-Time Control for Distribution Networks

Considering the possible overvoltage caused by high-penetration photovoltaics (PVs) connected to the distribution networks (DNs), a cluster partition-based voltage control combined day-ahead scheduling and real-time control for distribution networks is proposed. Firstly, a community detection algorithm utilizing a coupling quality function is introduced to divide the PVs into clusters. Based on the cluster partition, day-ahead scheduling (DAS) is proposed with the objective of minimizing the operating costs of PVs, as well as the on-load tap changer (OLTC). In the real-time control, a second-order cone programming (SOCP) model-based real-time voltage control (RTVC) strategy is drawn up in each cluster to regulate the PV inverters, and this strategy can correct the day-ahead scheduling by modifications. The proposed strategy realizes the combination of day-ahead scheduling and real-time voltage control, and the optimization of voltage control can be greatly simplified. Finally, the proposed method is applied to a practical 10 kV feeder to verify its effectiveness.

Fast computation of cluster validity measures for bregman divergences and benefits

Partitional clustering is one of the most relevant unsupervised learning and pattern recognition techniques. Unfortunately, one of the main drawbacks of these methodologies refer to the fact that the number of clusters is generally assumed to be known beforehand and automating its selection is not straightforward. On the same token, internal validity measures, such as the Silhouette index, Davies-Bouldin and Caliski-Harabasz measures have emerged as the standard techniques to be used when comparing the goodness of clustering results obtained via different clustering methods. These measures take into consideration both the inter and intra-cluster simmilarities and can be adapted to different metrics. Unfortunately, their used has been hindered due to their large computational complexities, which are commonly quadratic with respect to the number of instances of the data set. In this work, we show that the time complexity of computing the most popular internal validity measures can be utterly reduced by making used of the within-cluster errors and different properties of the Bregman divergences. This contribution ultimately allows us to massively speed-up the selection of an adequate number of clusters for a given data set as verified with extensive empirical comparisons.

Cluster partition for distributed energy resources in Regional Integrated Energy System

Fully utilizing local clean energy by regional Integrated Energy System is a effective way to alleviate energy crisis and reduce carbon emissions. Due to clean energy resources e.g., photovoltaic, wind power and low-grade heat distribute in region which results to be difficult to integrate, this paper provide improved two-steps k-means arithmetic for cluster partition of Regional Integrated Energy System for utilizing distributed energy. Firstly, the weight index is defined for direction of cluster partition. Secondly, according to the resource endowment and located position of distributed energy, the initial energy cluster partition and cluster center considering weight coefficient is determined. Finally, load is divided into the cluster according to the distance of source load and matching coefficient. The practical case indicate that the method proposed can effectively realize cluster partition and integration of distributed energy.

Equipment partition and control node location method for artificial colored-sand production line

According to the principle of regional centralization and overall decentralization, K-means algorithm based on elbow rule was adopted to divide the equipment on the artificial colored-sand production line into several clustering partitions. The results were optimized to realize power balance between different partitions. Center of gravity method was adopted to determine the location of each control node. The goal of minimizing the total weighted distance from each equipment to its corresponding control node was achieved. Field results have shown that hardware and wiring cost of the production line has decreased by 13.32% and 20.41%, respectively.

Stratification-based semi-supervised clustering algorithm for arbitrary shaped datasets

Semi-supervised clustering is not only an important branch of semi-supervised learning but also an improvement direction for clustering. Semi-supervised clustering algorithms designed based on Kmeans, such as the classical Seeded-Kmeans and Constrained-Kmeans, where supervision information is used to guide clustering iterations, have the same disadvantages as the original Kmeans algorithm: they are confined to the assumption of isotropic spherical clusters, leading to the narrow adaptability in handling data of various characteristics. To solve the problem, we propose the scattered centroids initialization clustering algorithm based on Stratification (SCICS). First, based on the concept of influence space, a method for modeling the cluster-level location of any object is presented, according to which we can obtain well-defined cluster decision boundaries through stratification. On this basis, by extending the seed thought, we propose a semi-supervised subclustering algorithm that can break through the limitations of partitional clustering methods that rely on strict assumptions on particular cluster distributions. Experiments on artificial and real-world datasets show that the proposed algorithm gains the ability of clustering arbitrary shaped data and surpasses the competitors in terms of performance and adaptability.

Cluster Partition Operation Study of Air-Cooled Fan Groups in a Natural Wind Disturbance

This study discusses the influence of natural wind on the air flow of air-cooled condensers (ACCs) and then proposes a partition speed-regulation strategy for a fan group with enhanced generalized capability, which is of great practical significance for optimizing energy-saving operations. The stochastic time-varying features of natural wind are characterized by sine–Gaussian, Weibull, and composed winds. In a natural wind disturbance, using the Sugon Supercomputing Center, the transient numerical simulation of the dynamic evolution of the ACC flow field was found: the dynamic system of air flow is a typical time-varying nonlinear process. Cluster analysis was used to extract the nonlinear features of air flow, divide the fan group into four subregions with generalization capability, and implement a partitioned speed operation. It was found that giving priority to increasing the fan speed in the headwind partition can suppress the natural wind disturbance and improve the overall air flow, thus reducing the fan speed in the leeward partition, which reduces the overall air flow loss. The dynamic characteristics of the fan group obtained from the simulation and the proposed fan partition method can guide the optimized energy-saving operation of ACCs.

Unsupervised clustering to differentiate rheumatoid arthritis patients based on proteomic signatures

Objective Patients with rheumatoid arthritis (RA) have different presentations and prognoses. Cluster analysis based on proteomic signatures creates independent phenogroups of patients with different pathophysiological backgrounds. We aimed to identify distinct pathophysiological clusters of RA patients based on circulating proteomic biomarkers. Method This was a cohort study including 399 RA patients. Clustering was performed on 94 circulating proteins (92 CVDII Olink®, high-sensitivity troponin T, and C-reactive protein). Unsupervised clustering was performed using a partitioning cluster algorithm. Results The clustering algorithm identified two distinct clusters: cluster 1 (n = 223) and cluster 2 (n = 176). Compared with cluster 1, cluster 2 included older patients with a higher burden of comorbidities (cardiovascular and RA related), more erosive and longer RA duration, more dyspnoea and fatigue, walking a shorter distance in the Six-Minute Walk Test, with more severe diastolic dysfunction, and a 4.5-fold higher risk of death or hospitalization for cardiovascular reasons. Tumour necrosis factor (TNF) receptor superfamily-related pathways were mainly responsible for the model’s discriminative ability. Conclusion Using unsupervised cluster analysis based on proteomic phenotypes, we identified two clusters of RA patients with distinct biomarkers profiles, clinical characteristics, and different outcomes that could reflect different pathophysiological backgrounds. TNF receptor superfamily-related proteins may be used to distinguish subgroups.

Robust hesitant fuzzy partitional clustering algorithms and their applications in decision making

Hesitant fuzzy sets (HFSs) are a powerful tool to describe uncertain and vague information, whose relationship can be analyzed and mined by clustering algorithms. The partitional idea is widely used in clustering analysis for real-number data but little for hesitant fuzzy data. After pointing out the weakness of the existing partitional clustering algorithms between HFSs, we modify the existing partitional clustering algorithms and propose four new algorithms with two types under hesitant fuzzy environment. One type, including the hesitant fuzzy K-medians (HFKME) and the hesitant fuzzy C-medians (HFCME) algorithms, is based on median but not mean. The other type, including the improved hesitant fuzzy K-means (IHFKM) and the improved hesitant fuzzy C-means (IFHCM) algorithms, is on the basis of a new and more robust distance measure which will be developed by HFSs. We find that these four new clustering algorithms are more robust than the existing ones and have better performance under the noise environment. After that, we compare our proposed partitional clustering algorithms with each other and also compare them with the existing methods, and then apply them to multi-attribute decision making and cluster analysis. Numerical results show that HFCME has better performance than HFKME, and IHFCM is better than IHFKM.

Abstract NG14: Dissecting immune microenvironment of T-cell acute lymphoblastic leukemia

Abstract NG14: Dissecting immune microenvironment of T-cell acute lymphoblastic leukemia